A Fuzzy ARTMAP Based on Quantitative Structure-Property Relationships (QSPRs) for Predicting Aqueous Solubility of Organic Compounds

Quantitative structure-property relationships (QSPRs) for estimating aqueous solubility of organic compounds at 25 degrees C were developed based on a fuzzy ARTMAP and a back-propagation neural networks using a heterogeneous set of 515 organic compounds. A set of molecular descriptors, developed from PM3 semiempirical MO-theory and topological descriptors (first-, second-, third-, and fourth-order molecular connectivity indices), were used as input parameters to the neural networks. Quantum chemical input descriptors included average polarizability, dipole moment, resonance energy, exchange energy, electron-nuclear attraction energy, and nuclear-nuclear (core-core) repulsion energy. The fuzzy ARTMAP/QSPR correlated aqueous solubility (S, mol/L) for a range of -11.62 to 4.31 logS with average absolute errors of 0.02 and 0.14 logS units for the overall and validation data sets, respectively. The optimal 11-13-1 back-propagation/QSPR model was less accurate, for the same solubility range, and exhibited larger average absolute errors of 0.29 and 0.28 logS units for the overall and validation sets, respectively. The fuzzy ARTMAP-based QSPR approach was shown to be superior to other back-propagation and multiple linear regression/QSPR models for aqueous solubility of organic compounds.

[1]  P. Isnard,et al.  Aqueous solubility and n-octanol/water partition coefficient correlations , 1989 .

[2]  Tony N. Rogers,et al.  Molecular Structure Disassembly Program (MOSDAP): A Chemical Information Model To Automate Structure-Based Physical Property Estimation , 1999, J. Chem. Inf. Comput. Sci..

[3]  R. Govind,et al.  Predicting soil sorption coefficients of organic chemicals using a neural network model , 1996 .

[4]  Guszti Bartfai,et al.  An improved learning algorithm for the fuzzy ARTMAP neural network , 1995, Proceedings 1995 Second New Zealand International Two-Stream Conference on Artificial Neural Networks and Expert Systems.

[5]  Peter C. Jurs,et al.  Quantitative Structure-Property Relationships for the Prediction of Vapor Pressures of Organic Compounds from Molecular Structures , 2000, J. Chem. Inf. Comput. Sci..

[6]  Shaomeng Wang,et al.  Estimation of aqueous solubility of organic molecules by the group contribution approach. Application to the study of biodegradation , 1992, J. Chem. Inf. Comput. Sci..

[7]  Stephen Grossberg,et al.  Fuzzy ART: Fast stable learning and categorization of analog patterns by an adaptive resonance system , 1991, Neural Networks.

[8]  Francesc Giralt,et al.  Correlation of activity coefficients of hydrocarbons in water at infinite dilution with molecular parameters , 1982 .

[9]  Peter C. Jurs,et al.  Prediction of Aqueous Solubility of Organic Compounds from Molecular Structure , 1998, J. Chem. Inf. Comput. Sci..

[10]  Paul Ruelle,et al.  Aqueous solubility prediction of environmentally important chemicals from the mobile order thermodynamics , 1997 .

[11]  N. Bodor,et al.  A new method for the estimation of partition coefficient , 1989 .

[12]  Igor V. Tetko,et al.  Neural Network Modeling for Estimation of Partition Coefficient Based on Atom-Type Electrotopological State Indices , 2000, J. Chem. Inf. Comput. Sci..

[13]  R. Mcweeny,et al.  Methods Of Molecular Quantum Mechanics , 1969 .

[14]  S. Yalkowsky,et al.  Solubility and partitioning I: Solubility of nonelectrolytes in water. , 1980, Journal of pharmaceutical sciences.

[15]  Yadu B. Tewari,et al.  AQUEOUS SOLUBILITIES, OCTANOL WATER PARTITION-COEFFICIENTS, AND ENTROPIES OF MELTING OF CHLORINATED BENZENES AND BIPHENYLS , 1984 .

[16]  Takahiro Suzuki,et al.  Development of an automatic estimation system for both the partition coefficient and aqueous solubility , 1991, J. Comput. Aided Mol. Des..

[17]  Bernd Beck,et al.  QM/NN QSPR Models with Error Estimation: Vapor Pressure and LogP , 2000, J. Chem. Inf. Comput. Sci..

[18]  Stephen Grossberg,et al.  The ART of adaptive pattern recognition by a self-organizing neural network , 1988, Computer.

[19]  Bernd Beck,et al.  Prediction of the n-Octanol/Water Partition Coefficient, logP, Using a Combination of Semiempirical MO-Calculations and a Neural Network , 1997 .

[20]  Alexandre Arenas,et al.  Neural Network Based Quantitative Structural Property Relations (QSPRs) for Predicting Boiling Points of Aliphatic Hydrocarbons , 2000, J. Chem. Inf. Comput. Sci..

[21]  Des Connell,et al.  Prediction of aqueous solubility and the octanol-water partition coefficient for lipophilic organic compounds using molecular descriptors and physicochemical properties , 1990 .

[22]  M. Karelson,et al.  Quantum-Chemical Descriptors in QSAR/QSPR Studies. , 1996, Chemical reviews.

[23]  S. Grossberg,et al.  A self-organizing neural network for supervised learning, recognition, and prediction , 1992, IEEE Communications Magazine.

[24]  M. Makino,et al.  Prediction of aqueous solubility coefficients of polychlorinated biphenyls by use of computer-calculated molecular properties , 1998 .

[25]  Jyrki Taskinen,et al.  Aqueous Solubility Prediction of Drugs Based on Molecular Topology and Neural Network Modeling , 1998, J. Chem. Inf. Comput. Sci..

[26]  Stephen Grossberg,et al.  A massively parallel architecture for a self-organizing neural pattern recognition machine , 1988, Comput. Vis. Graph. Image Process..

[27]  Guszti Bartfai,et al.  An ART-based modular architecture for learning hierarchical clusterings , 1996, Neurocomputing.

[28]  V. Buss,et al.  Quantum-mechanically calculated properties for the development of quantitative structure-activity relationships (QSAR'S). pKA-values of phenols and aromatic and aliphatic carboxylic acids , 1989 .

[29]  Cikui Liang,et al.  QSPR Prediction of Vapor Pressure from Solely Theoretically-Derived Descriptors , 1998, J. Chem. Inf. Comput. Sci..

[30]  P. Jurs,et al.  Development and use of charged partial surface area structural descriptors in computer-assisted quantitative structure-property relationship studies , 1990 .

[31]  Alan R. Katritzky,et al.  Correlation of the Aqueous Solubility of Hydrocarbons and Halogenated Hydrocarbons with Molecular Structure , 1998, J. Chem. Inf. Comput. Sci..

[32]  L. LoPinto.  Complying with OSHA's new safety law , 1993 .

[33]  Shuichi Miyamoto,et al.  A method for calculation of the aqueous solubility of organic compounds by using new fragment solubility constants. , 1986 .

[34]  S. Unger.  Molecular Connectivity in Structure–activity Analysis , 1987 .

[35]  Yilin Wang,et al.  QSPR Studies on Vapor Pressure, Aqueous Solubility, and the Prediction of Water-Air Partition Coefficients , 1998, J. Chem. Inf. Comput. Sci..

[36]  Heinz Sklenar,et al.  Molecular structure–biological activity relationships on the basis of quantum‐chemical calculations , 1979 .

[37]  Peter C. Jurs,et al.  Prediction of Aqueous Solubility for a Diverse Set of Heteroatom-Containing Organic Compounds Using a Quantitative Structure-Property Relationship , 1996, J. Chem. Inf. Comput. Sci..

[38]  G. S. Patil.  Correlation of aqueous solubility and octanol-water partition coefficient based on molecular structure , 1991 .

[39]  Jan Cz. Dobrowolski,et al.  Optimal molecular connectivity descriptors for nitrogen-containing molecules , 1998 .

[40]  Subhash C. Basak,et al.  Use of Topostructural, Topochemical, and Geometric Parameters in the Prediction of Vapor Pressure: A Hierarchical QSAR Approach , 1997, J. Chem. Inf. Comput. Sci..

[41]  M. Reinhard,et al.  Handbook for estimating physicochemical properties of organic compounds , 1999 .

[42]  G. Bartfai,et al.  Hierarchical clustering with ART neural networks , 1994, Proceedings of 1994 IEEE International Conference on Neural Networks (ICNN'94).

[43]  J. Stewart.  Optimization of parameters for semiempirical methods I. Method , 1989 .

[44]  R E Speece,et al.  Prediction of aqueous solubility of organic chemicals based on molecular structure. , 1988, Environmental science & technology.

[45]  D. B. Boyd.  Quantum Chemistry Program Exchange. , 1999, Journal of molecular graphics & modelling.

[46]  Stephen Grossberg,et al.  Fuzzy ARTMAP: A neural network architecture for incremental supervised learning of analog multidimensional maps , 1992, IEEE Trans. Neural Networks.

[47]  Ralph Kühne,et al.  Group contribution methods to estimate water solubility of organic chemicals , 1995 .

[48]  Xiang Pan,et al.  Water solubility data for 151 hydrocarbons , 1993 .

[49]  Tony N. Rogers,et al.  Molecular Structure Disassembly Program (MOSDAP): A Chemical Information Model to Automate Structure-Based Physical Property Estimation. , 1999 .

[50]  Robert Rallo,et al.  The simulation and interpretation of free turbulence with a cognitive neural system , 2000 .

[51]  Samuel H. Yalkowsky,et al.  Comment on “Prediction of Aqueous Solubility of Organic Chemicals Based on Molecular Structure. 2. Application to PNAs, PCBs, PCDDs, etc.” , 1989 .

[52]  G. Bartfai,et al.  An adaptive resonance theory-based neural network capable of learning via representational redescription , 1998, 1998 IEEE International Joint Conference on Neural Networks Proceedings. IEEE World Congress on Computational Intelligence (Cat. No.98CH36227).

[53]  Lemont B. Kier,et al.  A Shape Index from Molecular Graphs , 1985 .

[54]  L. Hall,et al.  Molecular connectivity in chemistry and drug research , 1976 .

[55]  Guszti Bartfai,et al.  On the match tracking anomaly of the ARTMAP neural network , 1996, Neural Networks.

[56]  James H. Wikel,et al.  The use of neural networks for variable selection in QSAR , 1993 .

[57]  M. Randic.  Characterization of molecular branching , 1975 .